On the Parallelization of MCMC for Community Detection

Wanye, Frank; Gleyzer, Vitaliy; Kao, Edward K.; Feng, Wu-chun

doi:10.1145/3545008.3545058

Cited by 5 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A parallel formulation of SBP was proposed in [13]. This formulation replaced the Metropolis-Hastings portion of the algorithm with a hybrid algorithm that processes informative, high-degree vertices sequentially and the less informative lowdegree vertices in parallel via an adaptation of asynchronous Gibbs sampling [18].…”

Section: B Stochastic Block Partitioningmentioning

confidence: 99%

“…To parallelize the computation within an MPI rank, we use our hybrid SBP [13] algorithm implemented using OpenMP.…”

Section: A C++ Divide-and-conquer Sbp Implementationmentioning

confidence: 99%

“…The synchronization of the blockmodels between ranks and the fact that each rank keeps track of the entire blockmodel means that the exact distributed SBP approach is likely to be slower and require more memory per rank than DC-SBP. At the same time, these weaknesses allow it to scale to a much higher number of ranks before accuracy degradation can be expected to set in (as n approaches V , EDiSt becomes equivalent to asynchronous Gibbs, which has previously been shown to degrade performance on some synthetic graphs [13]). On graphs with a particularly sparse dependency distribution, it is theoretically possible to scale the approach to V MPI ranks without any accuracy degradation.…”

Section: B Exact Distributed Sbpmentioning

confidence: 99%

“…When testing the divide-and-conquer approach, we noticed significant differences in how well the algorithm retains accuracy as the number of nodes increases based on the graph structure. On the Graph Challenge [11] graphs, the divideand-conquer approach maintained accuracy until between 8 and 16 MPI ranks; but on the web-graph-like graphs used in [13], the divide-and-conquer approach sometimes failed to maintain accuracy even with two MPI ranks. This is despite the fact that both sets of graphs were generated using a similar approach, using the blockmodel-based generator from the 'graph-tool' [23] Python library.…”

Section: A Synthetic Datasetsmentioning

confidence: 99%

“…There have been several attempts to accelerate SBP through sampling [12], shared memory parallelism [13], and various optimizations [14]. However, for the runtime of SBP to be practical on large-scale, real-world graphs, which often consist of upwards of millions of vertices and edges, the computation needs to be distributed across multiple compute nodes.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Exact Distributed Stochastic Block Partitioning

Wanye,

Gleyzer,

Kao

et al. 2023

2023 IEEE International Conference on Cluster Computing (CLUSTER)

Self Cite

View full text Add to dashboard Cite

Stochastic block partitioning (SBP) is a community detection algorithm that is highly accurate even on graphs with a complex community structure, but its inherently serial nature hinders its widespread adoption by the wider scientific community. To make it practical to analyze large real-world graphs with SBP, there is a growing need to parallelize and distribute the algorithm. The current state-of-the-art distributed SBP algorithm is a divide-and-conquer approach that limits communication between compute nodes until the end of inference. This leads to the breaking of computational dependencies, which causes convergence issues as the number of compute nodes increases and when the graph is sufficiently sparse. To address this shortcoming, we introduce EDiSt -an exact distributed stochastic block partitioning algorithm. Under EDiSt, compute nodes periodically share community assignments during inference. Due to this additional communication, EDiSt improves upon the divide-and-conquer algorithm by allowing it to scale out to a larger number of compute nodes without suffering from convergence issues, even on sparse graphs. We show that EDiSt provides speedups of up to 26.9× over the divide-and-conquer approach and speedups up to 44.0× over shared memory parallel SBP when scaled out to 64 compute nodes.

show abstract

Section: B Stochastic Block Partitioningmentioning

confidence: 99%

“…To parallelize the computation within an MPI rank, we use our hybrid SBP [13] algorithm implemented using OpenMP.…”

Section: A C++ Divide-and-conquer Sbp Implementationmentioning

confidence: 99%

Section: B Exact Distributed Sbpmentioning

confidence: 99%

Section: A Synthetic Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Exact Distributed Stochastic Block Partitioning

Wanye,

Gleyzer,

Kao

et al. 2023

2023 IEEE International Conference on Cluster Computing (CLUSTER)

Self Cite

View full text Add to dashboard Cite

show abstract

On the Multi-Dimensional Acceleration of Stochastic Blockmodeling for Community Detection

Wanye,

Feng

2023

2023 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops)

Self Cite

View full text Add to dashboard Cite

Stochastic block partitioning (SBP) is a community detection algorithm that is highly accurate even on graphs with a complex community structure. However, SBP is much slower than more commonly used algorithms, such as Louvain, making SBP impractical for analyzing large real-world graphs with millions of edges. Thus, we aim to realize fast and accurate community detection on large graphs by accelerating the highly accurate SBP algorithm via sampling, parallel and distributed computing on a cluster as well as algorithmic optimization. We compare our approach to other community detection algorithms, showing that SBP accelerated with our methods on 64 compute nodes is up to 1,163× faster than the official "Graph Challenge" baseline SBP implementation, while still being more accurate than the Louvain and Leiden algorithms on large graphs.

show abstract

uSAP: An Ultra-Fast Stochastic Graph Partitioner

Chang,

Huang

2023

2023 IEEE High Performance Extreme Computing Conference (HPEC)

View full text Add to dashboard Cite

On the Parallelization of MCMC for Community Detection

Cited by 5 publications

References 9 publications

Exact Distributed Stochastic Block Partitioning

Exact Distributed Stochastic Block Partitioning

On the Multi-Dimensional Acceleration of Stochastic Blockmodeling for Community Detection

uSAP: An Ultra-Fast Stochastic Graph Partitioner

Contact Info

Product

Resources

About